東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Attention-driven image interpretatio...

Fu, Hong.

FindBook

Google Book

Amazon

博客來

Attention-driven image interpretation, annotation and retrieval.

紀錄類型:	書目-語言資料,印刷品 : Monograph/item
正題名/作者:	Attention-driven image interpretation, annotation and retrieval./
作者:	Fu, Hong.
面頁冊數:	169 p.
附註:	Advisers: Zheru Chi; Dagan Feng.
Contained By:	Dissertation Abstracts International68-09B.
標題:	Computer Science. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3282329
ISBN:	9780549247500

Attention-driven image interpretation, annotation and retrieval.
Fu, Hong.

Attention-driven image interpretation, annotation and retrieval. - 169 p.

Advisers: Zheru Chi; Dagan Feng.

Thesis (Ph.D.)--Hong Kong Polytechnic University (Hong Kong), 2007.

This thesis presents novel attention-driven techniques for image interpretation, annotation and retrieval. Four main contributions are reported in the thesis. They include: (1) an attention-driven image interpretation method with application to image retrieval; (2) an efficient algorithm for attention-driven image interpretation from image segments; (3) a pre-classification technique to classify "attentive" images and "non-attentive" images and a combined retrieval strategy; and (4) a semantic network for image annotation by modelling attentive objects and their correlations.

ISBN: 9780549247500Subjects--Topical Terms:

626642
Computer Science.

Attention-driven image interpretation, annotation and retrieval.
LDR:04421nam 2200325 a 45 001 940680
005 20110518
008 110518s2007 ||||||||||||||||| ||eng d
020 $a 9780549247500
035 $a (UMI)AAI3282329
035 $a AAI3282329
040 $a UMI $c UMI
100 1 $a Fu, Hong. $3 1264811
245 1 0 $a Attention-driven image interpretation, annotation and retrieval.
300 $a 169 p.
500 $a Advisers: Zheru Chi; Dagan Feng.
500 $a Source: Dissertation Abstracts International, Volume: 68-09, Section: B, page: 6066.
502 $a Thesis (Ph.D.)--Hong Kong Polytechnic University (Hong Kong), 2007.
520 $a This thesis presents novel attention-driven techniques for image interpretation, annotation and retrieval. Four main contributions are reported in the thesis. They include: (1) an attention-driven image interpretation method with application to image retrieval; (2) an efficient algorithm for attention-driven image interpretation from image segments; (3) a pre-classification technique to classify "attentive" images and "non-attentive" images and a combined retrieval strategy; and (4) a semantic network for image annotation by modelling attentive objects and their correlations.
520 $a In the first investigation, we propose an attention-driven image interpretation method to pop out visually attentive objects from an image iteratively by maximizing a global attention function. In the method, an image is interpreted as containing several perceptually attended objects as well as the background, where each object is measured by an attention value. The attention values of attentive objects are then mapped to importance measures so as to facilitate the subsequent image retrieval. An attention-driven matching algorithm is proposed based on a retrieval strategy emphasizing attended objects. Experiments on 7376 Hemera color images annotated by keywords show that the retrieval results from our attention-driven approach compare favorably with conventional methods, especially when important objects are seriously concealed by the irrelevant background.
520 $a In the second investigation, the computation issue of an attention-driven image interpretation is addressed. The object reconstruction is a combinational optimization problem with a complexity of 2N which is computationally very expensive when the number of segments N is large. We formulate the attention-driven image interpretation process by a matrix representation. An efficient algorithm based on elementary transformations of the matrix is proposed to reduce the computational complexity to 3NN-12 2 . Experimental results on both synthetic and real data show an acceptable small degradation to the accuracy of object formulation while the processing speed is significantly increased.
520 $a In the third investigation, an all-season image retrieval system is proposed. The system can handle both the images with clearly attentive images and those without clearly attentive images. Firstly, considering the visual contrasts and spatial information of an image, a neural network is trained to classify it as an "attentive" or "non-attentive" image by using the Back Propagation Through Structure (BPTS) algorithm. In the second step, an "attentive" image is processed by an attentive retrieval strategy emphasizing attentive objects. Meanwhile, a "non-attentive" image is processed by a fusing-all retrieval system. An improved performance can be obtained by using this combined system.
520 $a In the fourth investigation, we propose an image annotation method based on attentively interpreted images. Firstly, a number of interpreted images are annotated manually as training samples. Secondly, a semantic network is constructed, which stores both the visual classifiers of attentive objects and the correlations among concepts. Finally, an annotation strategy is proposed to utilize the semantic network to annotate objects. Experimental results show that the trained semantic network is able to produce good annotation results, especially when a visual classifier does not produce a precise concept.
590 $a School code: 1170.
650 4 $a Computer Science. $3 626642
690 $a 0984
710 2 $a Hong Kong Polytechnic University (Hong Kong). $3 1020200
773 0 $t Dissertation Abstracts International $g 68-09B.
790 $a 1170
790 1 0 $a Chi, Zheru, $e advisor
790 1 0 $a Feng, Dagan, $e advisor
791 $a Ph.D.
792 $a 2007
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3282329